See360: Novel Panoramic View Interpolation.

We present See360, which is a versatile and efficient framework for 360° panoramic view interpolation using latent space viewpoint estimation. Most of the existing view rendering approaches only focus on indoor or synthetic 3D environments and render new views of small objects. In contrast, we suggest to tackle camera-centered view synthesis as a 2D affine transformation without using point clouds or depth maps, which enables an effective 360° panoramic scene exploration. Given a pair of reference images, the See360 model learns to render novel views by a proposed novel Multi-Scale Affine Transformer (MSAT), enabling the coarse-to-fine feature rendering. We also propose a Conditional Latent space AutoEncoder (C-LAE) to achieve view interpolation at any arbitrary angle. To show the versatility of our method, we introduce four training datasets, namely UrbanCity360, Archinterior360, HungHom360 and Lab360, which are collected from indoor and outdoor environments for both real and synthetic rendering. Experimental results show that the proposed method is generic enough to achieve real-time rendering of arbitrary views for all four datasets. In addition, our See360 model can be applied to view synthesis in the wild: with only a short extra training time (approximately 10 mins), and is able to render unknown real-world scenes. The superior performance of See360 opens up a promising direction for camera-centered view rendering and 360° panoramic view interpolation.

Features Guided Face Super-Resolution via Hybrid Model of Deep Learning and Random Forests.

Face hallucination or super-resolution is a practical application of general image super-resolution which has been recently studied by many researchers. The challenge of good face hallucination comes from a variety of poses, illuminations, facial expressions, and other degradations. In many proposed methods, researchers resolve it by using a generative neural network to reduce the perceptual loss so we can generate a photo-realistic image. The problem is that researchers usually overlook the fidelity of the super-resolved image which could affect further facial image processing. Meanwhile, many CNN based approaches cascade multiple networks to extract facial prior information to improve super-resolution quality. Because of the end-to-end design, the details are missing for investigation. In this paper, we combine new techniques in convolutional neural network and random forests to a Hierarchical CNN based Random Forests (HCRF) approach for face super-resolution in a coarse-to-fine manner. In the proposed approach, we focus on a general approach that can handle facial images with various conditions without pre-processing. To the best of our knowledge, this is the first paper that combines the advantages of deep learning with random forests for face super-resolution. To achieve superior performance, we propose two novel CNN models for coarse facial image super-resolution and segmentation and then apply new random forests to target on local facial features refinement making use of the segmentation results. Extensive benchmark experiments on subjective and objective evaluation show that HCRF can achieve comparable speed and competitive performance compared with state-of-the-art super-resolution approaches for very low-resolution images.

Nomogram to predict overall survival after gallbladder cancer resection in China.

AIM: To integrate clinically significant variables related to prognosis after curative resection for gallbladder carcinoma (GBC) into a predictive nomogram. METHODS: One hundred and forty-two GBC patients who underwent curative intent surgical resection at Peking Union Medical College Hospital (PUMCH) were included. This retrospective case study was conducted at PUMCH of the Chinese Academy of Medical Sciences and Peking Union Medical College (CAMS & PUMC) in China from January 1, 2003 to January 1, 2018. The continuous variable carbohydrate antigen 19-9 (CA19-9) was converted into a categorical variable (cCA19-9) based on the normal reference range. Stages 0 to IIIA were merged into one category, while the remaining stages were grouped into another category. Pathological grade X (GX) was treated as a missing value. A multivariate Cox proportional hazards model was used to select variables to construct a nomogram. Discrimination and calibration of the nomogram were performed via the concordance index (C-index) and calibration plots. The performance of the nomogram was estimated using the calibration curve. Receiver operating characteristic (ROC) curve analysis and decision curve analysis (DCA) were performed to evaluate the predictive accuracy and net benefit of the nomogram, respectively. RESULTS: Of these 142 GBC patients, 55 (38.7%) were male, and the median and mean age were 64 and 63.9 years, respectively. Forty-eight (33.8%) patients in this cohort were censored in the survival analysis. The median survival time was 20 months. A series of methods, including the likelihood ratio test and Akaike information criterion (AIC) as well as stepwise, forward, and backward analyses, were used to select the model, and all yielded identical results. Jaundice [hazard ratio (HR) = 2.9; 95% confidence interval (CI): 1.60-5.27], cCA19-9 (HR = 3.2; 95%CI: 1.91-5.39), stage (HR = 1.89; 95%CI: 1.16-3.09), and resection (R) (HR = 2.82; 95%CI: 1.54-5.16) were selected as significant predictors and combined into a survival time predictive nomogram (C-index = 0.803; 95%CI: 0.766-0.839). High prediction accuracy (adjusted C-index = 0.797) was further verified via bootstrap validation. The calibration plot demonstrated good performance of the nomogram. ROC curve analysis revealed a high sensitivity and specificity. A high net benefit was proven by DCA. CONCLUSION: A nomogram has been constructed to predict the overall survival of GBC patients who underwent radical surgery from a clinical database of GBC at PUMCH.